Low-rank adaptation

最近完整七日的证据

来源提及

6

前七日 1

不同来源

2

前期 1

可比较增长

不可比较

榜单记录

0

采集观测与无发布日期的记录，和有日期的原文提及分别统计。 七日观测：5 · 无日期记录：0

每日趋势 · 最多 90 天

柱形表示有日期的来源提及。最新 UTC 日可能尚未结束。零提及和缺少采集覆盖是不同情况。

虚线标记表示当日无记录，不作为零提及统计。

来源证据

当前展示证据的来源：arXiv 9 · Hugging Face Spaces 2 · GitHub Releases 1 · Hugging Face 1

1. arXiv · 原文发布 2026年11月5日

   Adapting Qwen3 to Tajik from 0.6B to 8B: Lower Text Loss Did Not Mean Better Understanding

   arXiv:2611.06062v1 Announce Type: new Abstract: Small LoRA adapters trained on Tajik news and books lowered Qwen3's Tajik text loss at every size we tried, from 0.6B to 8B, by 0.60 to 1.45 nats per token, but none of them improved Tajik reading comprehension where it can be measured. On Belebele the 1.7B and 8B adapters left accuracy unchanged and the 4B ada

   查看来源记录 →

2. arXiv · 原文发布 2026年11月2日

   KV-Cache Patching: Tracing How and Where Fine-Tuned Behaviors Arise

   arXiv:2610.41480v1 Announce Type: new Abstract: Fine-tuning a language model changes how it responds, but where is this fine-tuned behavior instantiated? To better understand this, we evaluate whether the change in model behavior arises only during the generation of the answer tokens where the change manifests, or whether altered processing of previous token

   查看来源记录 →

3. arXiv · 原文发布 2026年11月2日

   Enhancing Knowledge Entity Relation Extraction in Abstracts and Full-text Content of Academic Articles Using Large Language Models

   arXiv:2610.41552v1 Announce Type: new Abstract: This study investigates the effectiveness of large pre-trained language models (LLMs) for knowledge entity relation extraction (KERE) from academic papers. Existing studies have examined individual types of LLM-based strategies and evaluated model performance using metrics such as precision and recall. To provi

   查看来源记录 →

4. arXiv · 原文发布 2026年11月2日

   BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion

   arXiv:2610.41574v1 Announce Type: new Abstract: Unlike autoregressive (AR) models, diffusion language models (DLMs) permit parallel token updates, flexible generation, and bidirectional attention, but leading systems rely on costly pretraining or full-model fine-tuning. We present Build Your Own DLM (BYOD), a generalizable LoRA-only recipe for parameter-effi

   查看来源记录 →

5. arXiv · 原文发布 2026年11月2日

   Saidzoda-Tajik-LFM-2.6B: Adapting a 2.6B Hybrid Model to Tajik Tool Calling, and What Continued Pretraining Takes Away

   arXiv:2610.41576v1 Announce Type: new Abstract: We release Saidzoda-Tajik-LFM-2.6B, a Tajik adaptation of the 2.6B-parameter hybrid model LFM2.5-2.6B-Base, built for tool calling in Tajik on modest hardware. The recipe has two stages: LoRA continued pretraining (CPT) on 1,485,319 cleaned Tajik web documents for 3 epochs, then one epoch of supervised fine-tun

   查看来源记录 →

6. Hugging Face Spaces · 原文发布 2026年10月29日

   umaircxnd/MiniMax-H3-Turbo-Lora-UNCENSORED-Workflow

   Interactive demo built with gradio

7. arXiv · 原文发布 2026年10月29日

   LoRA on a Budget: Function-Aware Post-Hoc Compression for Adapter Fleets

   arXiv:2610.36386v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a key mechanism for efficiently specializing foundation models into many task- and user-specific variants. Serving many LoRA adapters under a shared resource budget turns post-hoc compression into a two-level allocation problem: rank must be distributed across layers within

   查看来源记录 →

8. arXiv · 原文发布 2026年10月22日

   Our Own Jev: Typed Decisions in One Forward Pass, from an In-House Judge to Open LoRA Models

   arXiv:2610.29052v1 Announce Type: new Abstract: A typed decision maps evidence, a question and a fixed set of options to a probability for every option, computed in one forward pass, by reading a language model's logits or a small head over its hidden states, instead of generating and parsing text. The commercial system Jev popularised this System~1 interfac

   查看来源记录 →

9. arXiv · 原文发布 2026年10月21日

   Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech Recognition

   arXiv:2610.26888v1 Announce Type: new Abstract: We present Mixture of Phonetic Experts based Low-Rank Adaptation (MoPE-LoRA), a parameter-efficient adaptation framework for accented English speech recognition. Recent mixture-of-experts approaches typically allocate experts per accent, implicitly treating accent identity as the primary axis of variation. In c

   查看来源记录 →

10. arXiv · 原文发布 2026年10月9日

    Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models

    查看来源记录 →

11. Hugging Face Spaces · 原文发布 2026年10月7日

    baka999/MiniMax-H3-Turbo-Lora-UNCENSORED

    Interactive demo built with gradio

12. GitHub Releases · 原文发布 2026年9月10日

    Release 5.17.0

    Release v5.17.0 New Model additions HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared expert and routes every token to 8 of them. The context window is 1M tokens. The architecture combines four features: Multi-head Latent Attent

    查看来源记录 →

13. Hugging Face · 原文发布 2026年9月10日

    Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

    查看来源记录 →

研究优先级 63 / 100

此分数用于排列研究候选，不是搜索量、预测结果或经过验证的商业需求。

• 证据数量

  22.5 / 30

  去重文章或首次观测；重复抓取不加分。

• 发布主体多样性

  16 / 25

  同主体保守归并，转载不增加独立证据。

• 可比变化

  0 / 20

  仅完整且可比的两周参与；零基线不计算百分比。

• 证据时效

  15 / 15

  依据最新发布或首次观测，不按重复采集时间刷新。

• 名称明确度

  9.7 / 10

  明确实体链接和技术概念优先于含义不明的缩写。

局限与解读

• 首次观测是采集记录的起点，不能证明词语或产品在全球首次出现。
• 计数仅代表已监测的公开来源，不代表全网热度或搜索需求。
• 本站首次发现时间不等于名称或概念的诞生时间。
• 候选来自公开标题、摘要和实体链接，并非已核实的全文分析。
• 来源多样性采用保守归并；未披露的转载或共同所有权仍可能无法识别。
• 已有概念或常见产品名，仅保留为历史基线，不视为新创造的词。
• 两周均需足够且可比较的采集覆盖，才判断增长。
• 该词的来源构成发生变化，或缺少可比较的基线。
• 近期证据包含发布三天后才采集的内容，暂不据此判断增长。
• 前一周样本过少，不展示容易误导的增长百分比。